Hugging Face Trending Papers June 10, 2026

Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models

Read the original on Hugging Face Trending Papers →

Sensitive personal information can appear in large-scale pre-training corpora for large language models (LLMs). Detecting and filtering such information is therefore essential to ensure compliance with privacy regulations and prevent unintended information leakage.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 16

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

arXiv:2606. 15396v1 Announce Type: cross Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns.

By Wenbo Yu, Bohua Wang, Hao Fang, Kuofeng Gao, Jingru Zeng, Xiaochen Yang, Tianyi Zhang, Xiaoxiao Ma, Jiawei Kong, Hao Wu, Bin Chen, Shu-Tao Xia, Min Zhang

llms rag benchmarks safety

arXiv AI

Jun 9

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

arXiv:2606. 09125v1 Announce Type: cross Abstract: Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information.

By Tiejin Chen, Pingzhi Li, Kaixiong Zhou, Tianlong Chen, Hua Wei

llms multimodal safety

Hugging Face Trending Papers

Jun 8

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information. However, Multi-modal Large Language Models (MLLMs), which process both text and images, introduce unique privacy challenges that remain underexplored.

llms multimodal safety

Hugging Face Trending Papers

Aug 11

Calibrating Post-Training Feature Shifts for LLM Data Contamination Detection

Large language models (LLMs) are trained on massive and largely undisclosed corpora that may contain copyrighted or privacy-sensitive content. Data contamination detection (DCD) therefore aims to determine whether a given text is a member of the pre-training corpus of a target LLM.

llms fine-tuning benchmarks safety

arXiv AI

Jul 28

PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window

arXiv:2607. 22695v1 Announce Type: new Abstract: Large Language Models (LLMs) are capable of generalizing human language for the completion of never-before-seen tasks, leading to widespread deployment.

By Ryan Thornton, Mir Mehedi Ahsan Pritom, Maanak Gupta

llms benchmarks safety

arXiv AI

Jun 9

Vision Language Model Helps Private Information De-Identification in Vision Data

arXiv:2606. 09132v1 Announce Type: new Abstract: Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability.

By Tiejin Chen, Pingzhi Li, Kaixiong Zhou, Tianlong Chen, Hua Wei

llms computer-vision multimodal safety

Related stories

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

Calibrating Post-Training Feature Shifts for LLM Data Contamination Detection

PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window

Vision Language Model Helps Private Information De-Identification in Vision Data